babybabellm-gpt_bert-ace-causal / original_project_config.json
haznitrama's picture
Add main & ema weights for ace
83fc419 verified
Raw
History Blame Contribute Delete
290 Bytes
{
"attention_probs_dropout_prob": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 384,
"intermediate_size": 1280,
"max_position_embeddings": 512,
"position_bucket_size": 32,
"num_attention_heads": 6,
"num_hidden_layers": 12,
"vocab_size": 8192,
"layer_norm_eps": 1e-05
}